A deep learning approach for understanding natural language commands for mobile service robots

TL;DR

This paper presents a deep learning system that interprets natural language commands for mobile service robots, combining LSTM-based intent detection, slot filling, and capability verification within a ROS framework, evaluated on standard datasets.

Contribution

It introduces an LSTM-based approach for intent detection and slot filling in robot commands, integrated with capability assessment and implemented as a ROS package.

Findings

LSTM networks outperform other RNN architectures in accuracy

Support Vector Machine effectively filters unsupported commands

System achieves competitive performance on benchmark datasets

Abstract

Using natural language to give instructions to robots is challenging, since natural language understanding is still largely an open problem. In this paper we address this problem by restricting our attention to commands modeled as one action, plus arguments (also known as slots). For action detection (also called intent detection) and slot filling various architectures of Recurrent Neural Networks and Long Short Term Memory (LSTM) networks were evaluated, having LSTMs achieved a superior accuracy. As the action requested may not fall within the robots capabilities, a Support Vector Machine(SVM) is used to determine whether it is or not. For the input of the neural networks, several word embedding algorithms were compared. Finally, to implement the system in a robot, a ROS package is created using a SMACH state machine. The proposed system is then evaluated both using well-known datasets and benchmarks in the context of domestic service robots.